{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:59:56Z","timestamp":1775815196947,"version":"3.50.1"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102003"],"award-info":[{"award-number":["2018AAA0102003"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771457"],"award-info":[{"award-number":["61771457"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702491"],"award-info":[{"award-number":["61702491"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Youth Innovation Promotion Association of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2020108"],"award-info":[{"award-number":["2020108"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015804","name":"China Computer Federation (CCF)-Baidu Open Fund","doi-asserted-by":"publisher","award":["2021PP15002000"],"award-info":[{"award-number":["2021PP15002000"]}],"id":[{"id":"10.13039\/100015804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3158546","type":"journal-article","created":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T21:42:15Z","timestamp":1648158135000},"page":"2726-2738","source":"Crossref","is-referenced-by-count":88,"title":["Long Short-Term Relation Transformer With Global Gating for Video Captioning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4660-8092","authenticated-orcid":false,"given":"Xingyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Jincan","family":"Deng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9525-9060","authenticated-orcid":false,"given":"Yunbin","family":"Tu","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology, Yunnan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2855422"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2916757"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988435"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028651"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042086"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051476"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref9","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"arXiv:1409.0473","author":"Bahdanau","year":"2014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. NeurIPS","author":"Vaswani"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref14","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. ICLR","author":"Kipf"},{"key":"ref15","first-page":"352","article-title":"A\u00b2-nets: Double attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref17","article-title":"Hybrid multiple attention network for semantic segmentation in aerial images","volume-title":"arXiv:2001.02870","author":"Niu","year":"2020"},{"key":"ref18","article-title":"Focal self-attention for local-global interactions in vision transformers","volume-title":"arXiv:2107.00641","author":"Yang","year":"2021"},{"key":"ref19","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. ICLR","author":"Veli\u010dkovi\u0107"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9512"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1213"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.127"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.108"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00013"},{"key":"ref27","article-title":"STAR: A benchmark for situated reasoning in real-world videos","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round)","author":"Wu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475473"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.01.018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107249"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.04.108"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123354"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref40","article-title":"Translating videos to natural language using deep recurrent neural networks","volume-title":"arXiv:1412.4729","author":"Venugopalan","year":"2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.662"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00901"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/104"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00852"},{"key":"ref48","first-page":"847","article-title":"TVT: Two-view transformer network for video captioning","volume-title":"Proc. ACML","author":"Chen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107075"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01067"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref58","first-page":"1","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yi"},{"key":"ref59","first-page":"1","article-title":"Grounding physical concepts of objects and events through visual reasoning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref60","article-title":"Scattering GCN: Overcoming oversmoothness in graph convolutional networks","volume-title":"arXiv:2003.08414","author":"Min","year":"2020"},{"key":"ref61","article-title":"Longformer: The long-document transformer","volume-title":"arXiv:2004.05150","author":"Beltagy","year":"2020"},{"key":"ref62","article-title":"Generating long sequences with sparse transformers","volume-title":"arXiv:1904.10509","author":"Child","year":"2019"},{"key":"ref63","article-title":"WaveNet: A generative model for raw audio","volume-title":"arXiv:1609.03499","author":"van den Oord","year":"2016"},{"key":"ref64","article-title":"Residual gated graph ConvNets","volume-title":"arXiv:1711.07553","author":"Bresson","year":"2017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_47"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102840"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.06.096"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107702"},{"key":"ref75","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Chen"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref79","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref81","article-title":"Microsoft COCO captions: Data collection and evaluation server","volume-title":"arXiv:1504.00325","author":"Chen","year":"2015"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref86","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"},{"key":"ref87","article-title":"Vision transformers with patch diversification","volume-title":"arXiv:2104.12753","author":"Gong","year":"2021"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CAHPC.2018.8645912"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09741388.pdf?arnumber=9741388","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T00:49:43Z","timestamp":1706057383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9741388\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3158546","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}